Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    column prop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    শনাল
    0.46
    잭
    0.40
    伈
    0.39
     dorsal
    0.38
    Bulletin
    0.38
    䚰
    0.38
    ={$
    0.38
    ویی
    0.37
     perinatal
    0.37
    ാനാ
    0.37
    POSITIVE LOGITS
     Ra
    0.46
    obra
    0.45
     Spiele
    0.42
     demostrar
    0.42
     OXIDES
    0.40
    Ra
    0.40
     EFFECT
    0.39
     bilden
    0.38
     Roskov
    0.38
     RA
    0.38
    Act Density 0.000%

    No Known Activations